Newer
Older
" <td>tak</td>\n",
" </tr>\n",
" <tr>\n",
" <th>39</th>\n",
" <td>CORRECT</td>\n",
" <td>ADV</td>\n",
" <td>samo</td>\n",
" <td>ADV</td>\n",
" <td>samo</td>\n",
" </tr>\n",
" <tr>\n",
" <th>40</th>\n",
" <td>VERB</td>\n",
" <td>dziękuję</td>\n",
" <td></td>\n",
" <td>NOUN</td>\n",
" <td>panu</td>\n",
" <td></td>\n",
" <th>42</th>\n",
" <td>DELETION</td>\n",
" <td>NOUN</td>\n",
" <td>dobranoc</td>\n",
" <td></td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>43</th>\n",
" <td>VERB</td>\n",
" <td>proszę</td>\n",
" <td>VERB</td>\n",
" <td>dziękuję</td>\n",
" <th>44</th>\n",
" <td>DELETION</td>\n",
" <td>ADV</td>\n",
" <td>bardzo</td>\n",
" <td></td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>45</th>\n",
" <td>NOUN</td>\n",
" <td>dobranoc</td>\n",
" <td>NOUN</td>\n",
" <td>dobranoc</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
" step_type reference_word_pos reference_word_text hypothesis_word_pos \\\n",
"0 CORRECT ADJ dobry ADJ \n",
"1 CORRECT NOUN wieczór NOUN \n",
"2 DELETION PRON xxx \n",
"3 CORRECT VERB słucham VERB \n",
"4 CORRECT ADJ dobry ADJ \n",
"5 CORRECT NOUN wieczór NOUN \n",
"6 CORRECT NOUN panu NOUN \n",
"7 CORRECT VERB mam VERB \n",
"8 CORRECT ADP do ADP \n",
"9 CORRECT NOUN pana NOUN \n",
"10 CORRECT NOUN prośbę NOUN \n",
"11 CORRECT VERB proszę VERB \n",
"12 CORRECT VERB zobaczyć VERB \n",
"13 CORRECT ADP z ADP \n",
"14 CORRECT NOUN pętli NOUN \n",
"15 CORRECT ADJ Szczęśliwickiej ADJ \n",
"16 CORRECT NUM sto NUM \n",
"17 DELETION NOUN osiemdziesiąt \n",
"18 SUBSTITUTION NUM cztery X \n",
"19 CORRECT ADV jutro ADV \n",
"20 CORRECT ADP w ADP \n",
"21 CORRECT NOUN sobotę NOUN \n",
"22 CORRECT ADP o ADP \n",
"23 CORRECT ADJ dwunastej ADJ \n",
"24 CORRECT CCONJ i CCONJ \n",
"25 CORRECT ADJ trzynastej ADJ \n",
"26 CORRECT VERB proszę VERB \n",
"27 CORRECT VERB podać VERB \n",
"28 DELETION NOUN rozkład \n",
"29 SUBSTITUTION ADJ dwunasta PRON \n",
"30 CORRECT NUM dwie NUM \n",
"31 CORRECT ADV tak ADV \n",
"32 CORRECT NUM dwadzieścia NUM \n",
"33 CORRECT NUM dwie NUM \n",
"34 CORRECT ADV tak ADV \n",
"35 CORRECT NUM czterdzieści NUM \n",
"36 CORRECT NUM dwie NUM \n",
"37 CORRECT NOUN trzynasta NOUN \n",
"38 CORRECT ADV tak ADV \n",
"39 CORRECT ADV samo ADV \n",
"40 DELETION VERB dziękuję \n",
"41 DELETION NOUN panu \n",
"42 DELETION NOUN dobranoc \n",
"43 CORRECT VERB proszę VERB \n",
"44 DELETION ADV bardzo \n",
"45 CORRECT NOUN dobranoc NOUN \n",
"\n",
" hypothesis_word_text \n",
"0 dobry \n",
"1 wieczór \n",
"2 \n",
"3 słucham \n",
"4 dobry \n",
"5 wieczór \n",
"6 panu \n",
"7 mam \n",
"8 do \n",
"9 pana \n",
"10 prośbę \n",
"11 proszę \n",
"12 zobaczyć \n",
"13 z \n",
"14 pętli \n",
"15 szczęśliwickiej \n",
"16 100 \n",
"17 \n",
"18 84 \n",
"19 jutro \n",
"20 w \n",
"21 sobotę \n",
"22 o \n",
"23 dwunastej \n",
"24 i \n",
"25 trzynastej \n",
"26 proszę \n",
"27 podać \n",
"28 \n",
"29 dwunasta \n",
"30 dwie \n",
"31 tak \n",
"32 20 \n",
"33 dwie \n",
"34 tak \n",
"35 40 \n",
"36 dwie \n",
"37 trzynasta \n",
"38 tak \n",
"39 samo \n",
"40 \n",
"41 \n",
"42 \n",
"43 dziękuję \n",
"44 \n",
"45 dobranoc "
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
"--------------------------------------------------------------\n",
"--------------------------------------------------------------\n",
"--------------------------------------------------------------\n"
]
}
],
"source": [
"for it in list(luna_record_provider.get_all_records())[:1]:\n",
" show_report_for(it, luna_experiment_repository, techmo_connections_config)"
]
},
{
"cell_type": "markdown",
"id": "a4b4f1bc-f0b3-4d23-bf1d-97f75715f332",
"metadata": {},
"source": [
"# Report for LUNA and AJN ASR"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "27797bad-c92a-45a6-87f2-071645c18150",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"record_id: LUNA.PL__KIEDY__DOBRAJAKOSC__F__2_2007-03-23_22_26_40__2_2007-03-23_22_26_40\n",
"properties_confiog: AJN ASR\n",
"\n",
"gold transcript: dobry wieczór xxx słucham dobry wieczór panu mam do pana prośbę proszę zobaczyć z pętli Szczęśliwickiej sto osiemdziesiąt cztery jutro w sobotę o dwunastej i trzynastej proszę podać rozkład dwunasta dwie tak dwadzieścia dwie tak czterdzieści dwie trzynasta tak samo dziękuję panu dobranoc proszę bardzo dobranoc\n",
"\n",
"asr transcript: dobry wieczór w sali oraz tak naprawdę <unk> tak jak ten nieszczęśliwi ta osiemdziesiąt te <unk> to taka zabawa - <unk> <unk> <unk> ta sięga tej szepeta stąd tak od pieszczot tak czterdziestu trzech stoczni kieruje się na dobranoc \n",
"\n",
"word wer {'classic_wer': 1.0}\n",
"\n",
"pos wer {'classic_wer': 0.8478260869565217}\n",
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
"\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>step_type</th>\n",
" <th>reference_word_text</th>\n",
" <th>hypothesis_word_text</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>DELETION</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>DELETION</td>\n",
" <td>wieczór</td>\n",
" <td></td>\n",
" <td>DELETION</td>\n",
" <td>xxx</td>\n",
" <td></td>\n",
" <td>DELETION</td>\n",
" <td>słucham</td>\n",
" <td></td>\n",
" <td>SUBSTITUTION</td>\n",
" <td>wieczór</td>\n",
" <td>{'id': '0fc83ca6-3db7-467e-8b86-8ef06ab2925e',...</td>\n",
" <td>SUBSTITUTION</td>\n",
" <td>panu</td>\n",
" <td>{'id': 'b79a7ca0-a06c-4d53-8e3d-22d3083fb686',...</td>\n",
" <td>SUBSTITUTION</td>\n",
" <td>mam</td>\n",
" <td>{'id': 'e3369ffb-9227-4ced-84b5-a8ff03217a29',...</td>\n",
" <td>SUBSTITUTION</td>\n",
" <td>do</td>\n",
" <td>{'id': 'f9381602-91db-4386-acc7-c2a68b881740',...</td>\n",
" <td>SUBSTITUTION</td>\n",
" <td>pana</td>\n",
" <td>{'id': '72899e49-378e-449b-aa53-81eec263d952',...</td>\n",
" <td>SUBSTITUTION</td>\n",
" <td>prośbę</td>\n",
" <td>{'id': '15386238-0769-43e0-a952-71f680c3aaf6',...</td>\n",
" <td>SUBSTITUTION</td>\n",
" <td>proszę</td>\n",
" <td>{'id': 'e15a3678-43eb-44a3-8d7f-d929dc2eed65',...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>SUBSTITUTION</td>\n",
" <td>zobaczyć</td>\n",
" <td>{'id': 'a8d6415d-6b7f-4c22-a630-7f92d5cf91f2',...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>SUBSTITUTION</td>\n",
" <td>z</td>\n",
" <td>{'id': 'bf930234-2543-4654-b0fc-f8ce87265a80',...</td>\n",
" <td>SUBSTITUTION</td>\n",
" <td>pętli</td>\n",
" <td>{'id': 'dd419ef1-fe5b-4749-ad7f-650434b8eef0',...</td>\n",
" <td>SUBSTITUTION</td>\n",
" <td>Szczęśliwickiej</td>\n",
" <td>{'id': 'a816b0e1-9eeb-4b84-b3ad-ec408f1276f9',...</td>\n",
" <td>SUBSTITUTION</td>\n",
" <td>sto</td>\n",
" <td>{'id': '599a695d-3e8c-4724-b589-53f2731e3fb7',...</td>\n",
" <td>SUBSTITUTION</td>\n",
" <td>osiemdziesiąt</td>\n",
" <td>{'id': '4e689ada-9908-4fde-b912-77ebf5e58da3',...</td>\n",
" <td>SUBSTITUTION</td>\n",
" <td>cztery</td>\n",
" <td>{'id': '20a48869-e027-4f83-a088-cef33d42d5bc',...</td>\n",
" <td>SUBSTITUTION</td>\n",
" <td>jutro</td>\n",
" <td>{'id': '4c644c3f-1089-410d-9c29-6d76b794271c',...</td>\n",
" <td>SUBSTITUTION</td>\n",
" <td>w</td>\n",
" <td>{'id': 'c36d145a-d458-4d1a-a964-659f82c366c4',...</td>\n",
" <td>SUBSTITUTION</td>\n",
" <td>sobotę</td>\n",
" <td>{'id': '4f750ee1-508f-4eae-b8d7-e19aeb111a8f',...</td>\n",
" <td>SUBSTITUTION</td>\n",
" <td>o</td>\n",
" <td>{'id': '67d24325-7df4-4034-8986-dc77f7bb7676',...</td>\n",
" <td>SUBSTITUTION</td>\n",
" <td>dwunastej</td>\n",
" <td>{'id': '4fe1a03c-22ad-49f1-a128-929d10ed79b4',...</td>\n",
" <td>SUBSTITUTION</td>\n",
" <td>i</td>\n",
" <td>{'id': 'a89a555d-bc10-440d-b9d1-6246fcffe164',...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25</th>\n",
" <td>SUBSTITUTION</td>\n",
" <td>trzynastej</td>\n",
" <td>{'id': '5f27424d-08dd-4be0-af06-69e25db0b6e3',...</td>\n",
" <td>SUBSTITUTION</td>\n",
" <td>proszę</td>\n",
" <td>{'id': '9d765c98-6f5d-4891-bf01-c032de915124',...</td>\n",
" <td>SUBSTITUTION</td>\n",
" <td>podać</td>\n",
" <td>{'id': 'a31f5e9a-3fa2-4dec-b150-5d29d60eb5c2',...</td>\n",
" <td>SUBSTITUTION</td>\n",
" <td>rozkład</td>\n",
" <td>{'id': '81d6bccb-4b96-4f5c-b4d5-f8565e7cdf21',...</td>\n",
" <td>SUBSTITUTION</td>\n",
" <td>dwunasta</td>\n",
" <td>{'id': 'da6703c2-c671-4456-a3c6-05faabe74a85',...</td>\n",
" <td>SUBSTITUTION</td>\n",
" <td>dwie</td>\n",
" <td>{'id': '18245e17-744c-4b75-986a-de684620fa2a',...</td>\n",
" <td>SUBSTITUTION</td>\n",
" <td>tak</td>\n",
" <td>{'id': '9a072368-4e9e-4322-8b8d-ab070a85a991',...</td>\n",
" <td>SUBSTITUTION</td>\n",
" <td>dwadzieścia</td>\n",
" <td>{'id': 'e9d7ced3-34ef-4c61-9dd3-8baaf9691bd2',...</td>\n",
" <td>SUBSTITUTION</td>\n",
" <td>dwie</td>\n",
" <td>{'id': 'be21e530-ef75-471e-9759-88aed98c71cf',...</td>\n",
" <td>SUBSTITUTION</td>\n",
" <td>tak</td>\n",
" <td>{'id': '63b9b0ed-3ff6-4641-a1da-f549cd60de5b',...</td>\n",
" <td>SUBSTITUTION</td>\n",
" <td>czterdzieści</td>\n",
" <td>{'id': 'a5a989c4-ad31-4fb2-aba9-a8d20e8b4a65',...</td>\n",
" <td>SUBSTITUTION</td>\n",
" <td>dwie</td>\n",
" <td>{'id': '30b305da-22b6-4cca-8c37-e77ba91871d6',...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>37</th>\n",
" <td>SUBSTITUTION</td>\n",
" <td>trzynasta</td>\n",
" <td>{'id': '6432c35f-2f01-40bb-a781-cc350df86f17',...</td>\n",
" <td>SUBSTITUTION</td>\n",
" <td>tak</td>\n",
" <td>{'id': '9990a320-4957-49cb-ba0e-90335e333980',...</td>\n",
" <td>SUBSTITUTION</td>\n",
" <td>samo</td>\n",
" <td>{'id': '62544cbd-07c7-4490-9bf1-b53d18fff6be',...</td>\n",
" <td>SUBSTITUTION</td>\n",
" <td>dziękuję</td>\n",
" <td>{'id': '7ed7d25f-34bd-4ab2-9619-fab5b729bc62',...</td>\n",
" <td>SUBSTITUTION</td>\n",
" <td>panu</td>\n",
" <td>{'id': '2089df9b-aff1-4f3e-8734-d63cbef4ee2d',...</td>\n",
" <td>SUBSTITUTION</td>\n",
" <td>dobranoc</td>\n",
" <td>{'id': 'e739993a-39b1-4a19-8300-ff75fb32ef2f',...</td>\n",
" <td>SUBSTITUTION</td>\n",
" <td>proszę</td>\n",
" <td>{'id': 'afb1404c-de1f-4d97-9693-955d123f8642',...</td>\n",
" <td>SUBSTITUTION</td>\n",
" <td>bardzo</td>\n",
" <td>{'id': '95599cf6-0c6f-4621-b3d0-0464e7ac37a9',...</td>\n",
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
" <td>SUBSTITUTION</td>\n",
" <td>dobranoc</td>\n",
" <td>{'id': 'b85a106b-f158-40ab-9378-dd93758cbd3e',...</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" step_type reference_word_text \\\n",
"0 DELETION dobry \n",
"1 DELETION wieczór \n",
"2 DELETION xxx \n",
"3 DELETION słucham \n",
"4 DELETION dobry \n",
"5 SUBSTITUTION wieczór \n",
"6 SUBSTITUTION panu \n",
"7 SUBSTITUTION mam \n",
"8 SUBSTITUTION do \n",
"9 SUBSTITUTION pana \n",
"10 SUBSTITUTION prośbę \n",
"11 SUBSTITUTION proszę \n",
"12 SUBSTITUTION zobaczyć \n",
"13 SUBSTITUTION z \n",
"14 SUBSTITUTION pętli \n",
"15 SUBSTITUTION Szczęśliwickiej \n",
"16 SUBSTITUTION sto \n",
"17 SUBSTITUTION osiemdziesiąt \n",
"18 SUBSTITUTION cztery \n",
"19 SUBSTITUTION jutro \n",
"20 SUBSTITUTION w \n",
"21 SUBSTITUTION sobotę \n",
"22 SUBSTITUTION o \n",
"23 SUBSTITUTION dwunastej \n",
"24 SUBSTITUTION i \n",
"25 SUBSTITUTION trzynastej \n",
"26 SUBSTITUTION proszę \n",
"27 SUBSTITUTION podać \n",
"28 SUBSTITUTION rozkład \n",
"29 SUBSTITUTION dwunasta \n",
"30 SUBSTITUTION dwie \n",
"31 SUBSTITUTION tak \n",
"32 SUBSTITUTION dwadzieścia \n",
"33 SUBSTITUTION dwie \n",
"34 SUBSTITUTION tak \n",
"35 SUBSTITUTION czterdzieści \n",
"36 SUBSTITUTION dwie \n",
"37 SUBSTITUTION trzynasta \n",
"38 SUBSTITUTION tak \n",
"39 SUBSTITUTION samo \n",
"40 SUBSTITUTION dziękuję \n",
"41 SUBSTITUTION panu \n",
"42 SUBSTITUTION dobranoc \n",
"43 SUBSTITUTION proszę \n",
"44 SUBSTITUTION bardzo \n",
"45 SUBSTITUTION dobranoc \n",
"\n",
" hypothesis_word_text \n",
"0 \n",
"1 \n",
"2 \n",
"3 \n",
"4 \n",
"5 {'id': '0fc83ca6-3db7-467e-8b86-8ef06ab2925e',... \n",
"6 {'id': 'b79a7ca0-a06c-4d53-8e3d-22d3083fb686',... \n",
"7 {'id': 'e3369ffb-9227-4ced-84b5-a8ff03217a29',... \n",
"8 {'id': 'f9381602-91db-4386-acc7-c2a68b881740',... \n",
"9 {'id': '72899e49-378e-449b-aa53-81eec263d952',... \n",
"10 {'id': '15386238-0769-43e0-a952-71f680c3aaf6',... \n",
"11 {'id': 'e15a3678-43eb-44a3-8d7f-d929dc2eed65',... \n",
"12 {'id': 'a8d6415d-6b7f-4c22-a630-7f92d5cf91f2',... \n",
"13 {'id': 'bf930234-2543-4654-b0fc-f8ce87265a80',... \n",
"14 {'id': 'dd419ef1-fe5b-4749-ad7f-650434b8eef0',... \n",
"15 {'id': 'a816b0e1-9eeb-4b84-b3ad-ec408f1276f9',... \n",
"16 {'id': '599a695d-3e8c-4724-b589-53f2731e3fb7',... \n",
"17 {'id': '4e689ada-9908-4fde-b912-77ebf5e58da3',... \n",
"18 {'id': '20a48869-e027-4f83-a088-cef33d42d5bc',... \n",
"19 {'id': '4c644c3f-1089-410d-9c29-6d76b794271c',... \n",
"20 {'id': 'c36d145a-d458-4d1a-a964-659f82c366c4',... \n",
"21 {'id': '4f750ee1-508f-4eae-b8d7-e19aeb111a8f',... \n",
"22 {'id': '67d24325-7df4-4034-8986-dc77f7bb7676',... \n",
"23 {'id': '4fe1a03c-22ad-49f1-a128-929d10ed79b4',... \n",
"24 {'id': 'a89a555d-bc10-440d-b9d1-6246fcffe164',... \n",
"25 {'id': '5f27424d-08dd-4be0-af06-69e25db0b6e3',... \n",
"26 {'id': '9d765c98-6f5d-4891-bf01-c032de915124',... \n",
"27 {'id': 'a31f5e9a-3fa2-4dec-b150-5d29d60eb5c2',... \n",
"28 {'id': '81d6bccb-4b96-4f5c-b4d5-f8565e7cdf21',... \n",
"29 {'id': 'da6703c2-c671-4456-a3c6-05faabe74a85',... \n",
"30 {'id': '18245e17-744c-4b75-986a-de684620fa2a',... \n",
"31 {'id': '9a072368-4e9e-4322-8b8d-ab070a85a991',... \n",
"32 {'id': 'e9d7ced3-34ef-4c61-9dd3-8baaf9691bd2',... \n",
"33 {'id': 'be21e530-ef75-471e-9759-88aed98c71cf',... \n",
"34 {'id': '63b9b0ed-3ff6-4641-a1da-f549cd60de5b',... \n",
"35 {'id': 'a5a989c4-ad31-4fb2-aba9-a8d20e8b4a65',... \n",
"36 {'id': '30b305da-22b6-4cca-8c37-e77ba91871d6',... \n",
"37 {'id': '6432c35f-2f01-40bb-a781-cc350df86f17',... \n",
"38 {'id': '9990a320-4957-49cb-ba0e-90335e333980',... \n",
"39 {'id': '62544cbd-07c7-4490-9bf1-b53d18fff6be',... \n",
"40 {'id': '7ed7d25f-34bd-4ab2-9619-fab5b729bc62',... \n",
"41 {'id': '2089df9b-aff1-4f3e-8734-d63cbef4ee2d',... \n",
"42 {'id': 'e739993a-39b1-4a19-8300-ff75fb32ef2f',... \n",
"43 {'id': 'afb1404c-de1f-4d97-9693-955d123f8642',... \n",
"44 {'id': '95599cf6-0c6f-4621-b3d0-0464e7ac37a9',... \n",
"45 {'id': 'b85a106b-f158-40ab-9378-dd93758cbd3e',... "
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>step_type</th>\n",
" <th>reference_word_pos</th>\n",
" <th>reference_word_text</th>\n",
" <th>hypothesis_word_pos</th>\n",
" <th>hypothesis_word_text</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>ADJ</td>\n",
" <td>dobry</td>\n",
" <td>ADJ</td>\n",
" <td>dobry</td>\n",
" <th>1</th>\n",
" <td>CORRECT</td>\n",
" <td>NOUN</td>\n",
" <td>wieczór</td>\n",
" <td>NOUN</td>\n",
" <td>wieczór</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>DELETION</td>\n",
" <td>xxx</td>\n",
" <td></td>\n",
" <td></td>\n",
" <th>3</th>\n",
" <td>DELETION</td>\n",
" <td>VERB</td>\n",
" <td>słucham</td>\n",
" <td></td>\n",
" <td></td>\n",
" <th>6</th>\n",
" <td>SUBSTITUTION</td>\n",
" <td>NOUN</td>\n",
" <td>panu</td>\n",
" <td>CCONJ</td>\n",
" <td>oraz</td>\n",
" <th>7</th>\n",
" <td>SUBSTITUTION</td>\n",
" <td>VERB</td>\n",
" <td>mam</td>\n",
" <td>PART</td>\n",
" <td>tak</td>\n",
" <td>do</td>\n",
" <td>PART</td>\n",
" <td>naprawdę</td>\n",
" <th>10</th>\n",
" <td>SUBSTITUTION</td>\n",
" <td>NOUN</td>\n",
" <td>prośbę</td>\n",
" <td>X</td>\n",
" <td>unk</td>\n",
" <td>proszę</td>\n",
" <td>PUNCT</td>\n",
" <td>></td>\n",
" <td>zobaczyć</td>\n",
" <td>ADV</td>\n",
" <td>tak</td>\n",
" <td>z</td>\n",
" <td>SCONJ</td>\n",
" <td>jak</td>\n",
" <td>pętli</td>\n",
" <td>DET</td>\n",
" <td>ten</td>\n",
" <th>16</th>\n",
" <td>INSERTION</td>\n",
" <td></td>\n",
" <td></td>\n",
" <td>DET</td>\n",
" <td>ta</td>\n",
" <td>NUM</td>\n",
" <td>sto</td>\n",
" <td>NUM</td>\n",
" <td>osiemdziesiąt</td>\n",
" <td>cztery</td>\n",
" <td>PUNCT</td>\n",
" <td>></td>\n",
" <th>22</th>\n",
" <td>SUBSTITUTION</td>\n",
" <td>ADV</td>\n",
" <td>jutro</td>\n",
" <td>AUX</td>\n",
" <td>to</td>\n",
" <th>23</th>\n",
" <td>SUBSTITUTION</td>\n",
" <td>ADP</td>\n",
" <td>w</td>\n",
" <td>DET</td>\n",
" <td>taka</td>\n",
" <td>NOUN</td>\n",
" <td>sobotę</td>\n",
" <td>NOUN</td>\n",
" <td>zabawa</td>\n",
" <th>25</th>\n",
" <td>INSERTION</td>\n",
" <td></td>\n",
" <td></td>\n",
" <td>PUNCT</td>\n",
" <td>-</td>\n",
" <th>26</th>\n",
" <td>INSERTION</td>\n",
" <td></td>\n",
" <td></td>\n",
" <td>PUNCT</td>\n",
" <td><</td>\n",
" </tr>\n",
" <tr>\n",
" <th>27</th>\n",
" <th>28</th>\n",
" <td>SUBSTITUTION</td>\n",
" <td>ADJ</td>\n",
" <td>dwunastej</td>\n",
" <td>PUNCT</td>\n",
" <td>></td>\n",
" <th>30</th>\n",
" <td>SUBSTITUTION</td>\n",
" <td>ADJ</td>\n",
" <td>trzynastej</td>\n",
" <td>PROPN</td>\n",
" <td>unk</td>\n",
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
" <th>31</th>\n",
" <td>SUBSTITUTION</td>\n",
" <td>VERB</td>\n",
" <td>proszę</td>\n",
" <td>PUNCT</td>\n",
" <td>></td>\n",
" </tr>\n",
" <tr>\n",
" <th>32</th>\n",
" <td>SUBSTITUTION</td>\n",
" <td>VERB</td>\n",
" <td>podać</td>\n",
" <td>PUNCT</td>\n",
" <td><</td>\n",
" </tr>\n",
" <tr>\n",
" <th>33</th>\n",
" <td>CORRECT</td>\n",
" <td>NOUN</td>\n",
" <td>rozkład</td>\n",
" <td>NOUN</td>\n",
" <td>unk</td>\n",
" </tr>\n",
" <tr>\n",
" <th>34</th>\n",
" <td>SUBSTITUTION</td>\n",
" <td>dwunasta</td>\n",
" <td>PUNCT</td>\n",
" <td>></td>\n",
" <th>35</th>\n",
" <td>SUBSTITUTION</td>\n",
" <td>NUM</td>\n",
" <td>dwie</td>\n",
" <td>DET</td>\n",
" <td>ta</td>\n",
" </tr>\n",
" <tr>\n",
" <th>36</th>\n",
" <td>SUBSTITUTION</td>\n",
" <td>ADV</td>\n",
" <td>tak</td>\n",
" <td>VERB</td>\n",
" <td>sięga</td>\n",
" </tr>\n",
" <tr>\n",
" <th>37</th>\n",
" <td>SUBSTITUTION</td>\n",
" <td>dwie</td>\n",
" <td>NOUN</td>\n",
" <td>szepeta</td>\n",
" <td>ADV</td>\n",
" <td>tak</td>\n",
" <td>ADV</td>\n",
" <td>stąd</td>\n",
" <td>czterdzieści</td>\n",
" <td>ADV</td>\n",
" <td>tak</td>\n",
" <td>dwie</td>\n",
" <td>ADP</td>\n",
" <td>od</td>\n",
" <th>42</th>\n",
" <td>CORRECT</td>\n",
" <td>NOUN</td>\n",
" <td>trzynasta</td>\n",
" <td>NOUN</td>\n",
" <td>pieszczot</td>\n",